© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12839
    Prev
    Next
    INDEX
    Explanations

    unconstrained, endogenous, features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PropertyValue
    -0.08
    åIJĮæŃ¥
    -0.07
     raci
    -0.07
    æĶ«
    -0.07
    è°IJ
    -0.07
    æľīå¿ĥ
    -0.07
    åĽŀèIJ½
    -0.06
    èĦī
    -0.06
    okter
    -0.06
    Sync
    -0.06
    POSITIVE LOGITS
    kos
    0.08
     handel
    0.08
    icken
    0.08
     conversion
    0.08
    conversion
    0.07
     Converted
    0.07
    æł¼å¼ı
    0.07
    urd
    0.07
    转æį¢
    0.07
    è½īæıĽ
    0.07
    Activations Density 0.001%

    No Known Activations